The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination". Initial retrieval-augmented generation (RAG) methods like the "Retrieve-Read" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach, Curriculum Assistant Learning and Reinforced Preference Optimization. AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.

翻译：大型语言模型（LLMs）的出现显著推动了自然语言处理的发展，但这些模型常常生成事实性错误的信息，即所谓的“幻觉”问题。早期的检索增强生成（RAG）方法，如“检索-阅读”框架，在处理复杂推理任务时表现不足。后续基于提示的RAG策略和监督微调（SFT）方法虽提升了性能，但需要频繁重新训练，且存在改变LLM基础能力的风险。为应对这些挑战，我们提出了基于助手的检索增强生成（AssistRAG），在LLM中集成了一个智能信息助手。该助手通过工具使用、动作执行、记忆构建和计划制定来管理记忆与知识。采用两阶段训练方法——课程助手学习和强化偏好优化，AssistRAG增强了信息检索与决策能力。实验表明，AssistRAG在各项基准测试中均显著优于现有方法，尤其能提升能力相对较弱LLM的性能，为其提供更优的推理能力和更准确的回答。